Files
cburn/internal/pipeline/loader.go
teernisse 24454247a3 feat: add data pipeline with parallel loading, aggregation, and cache integration
Implement the pipeline layer that orchestrates discovery, parsing,
caching, and aggregation:

- pipeline/loader.go: Load() discovers session files via ScanDir,
  optionally filters out subagent files, then parses all files in
  parallel using a bounded worker pool sized to GOMAXPROCS. Workers
  read from a pre-filled channel (no contention on dispatch) and
  report progress via an atomic counter and callback. LoadResult
  tracks total files, parsed files, parse errors, and file errors.

- pipeline/aggregator.go: Five aggregation functions, all operating
  on time-filtered session slices:

  * Aggregate: computes SummaryStats across all sessions — total
    tokens (5 types), estimated cost, cache savings (summed per-model
    via config.CalculateCacheSavings), cache hit rate, and per-active-
    day rates (cost, tokens, sessions, prompts, minutes).

  * AggregateDays: groups sessions by local calendar date, sorted
    most-recent-first.

  * AggregateModels: groups by normalized model name with share
    percentages, sorted by cost descending.

  * AggregateProjects: groups by project name, sorted by cost.

  * AggregateHourly: distributes prompt/session/token counts across
    24 hour buckets (attributed to session start hour).

  Also provides FilterByTime, FilterByProject, FilterByModel with
  case-insensitive substring matching.

- pipeline/incremental.go: LoadWithCache() implements the incremental
  loading strategy — compares discovered files against the cache's
  file_tracker (mtime_ns + size), loads unchanged sessions from
  SQLite, and only reparses files that changed. Reparsed results
  are immediately saved back to cache. CacheDir/CachePath follow
  XDG_CACHE_HOME convention (~/.cache/cburn/metrics.db).

- pipeline/bench_test.go: Benchmarks for ScanDir, ParseFile (worst-
  case largest file), full Load, and LoadWithCache to measure the
  incremental cache speedup.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 13:01:56 -05:00

118 lines
2.4 KiB
Go

package pipeline
import (
"fmt"
"runtime"
"sync"
"sync/atomic"
"cburn/internal/model"
"cburn/internal/source"
)
// LoadResult holds the output of the full data loading pipeline.
type LoadResult struct {
Sessions []model.SessionStats
TotalFiles int
ParsedFiles int
ParseErrors int
FileErrors int
ProjectCount int
}
// ProgressFunc is called during loading to report progress.
// current is the number of files processed so far, total is the total count.
type ProgressFunc func(current, total int)
// Load discovers and parses all session files from the Claude data directory.
// It uses a bounded worker pool for parallel parsing.
func Load(claudeDir string, includeSubagents bool, progressFn ProgressFunc) (*LoadResult, error) {
// Discover files
files, err := source.ScanDir(claudeDir)
if err != nil {
return nil, fmt.Errorf("scanning %s: %w", claudeDir, err)
}
if len(files) == 0 {
return &LoadResult{}, nil
}
// Filter subagents if requested
var toProcess []source.DiscoveredFile
if includeSubagents {
toProcess = files
} else {
for _, f := range files {
if !f.IsSubagent {
toProcess = append(toProcess, f)
}
}
}
result := &LoadResult{
TotalFiles: len(toProcess),
ProjectCount: source.CountProjects(files),
}
if len(toProcess) == 0 {
return result, nil
}
// Parallel parsing with bounded worker pool
numWorkers := runtime.GOMAXPROCS(0)
if numWorkers < 1 {
numWorkers = 4
}
if numWorkers > len(toProcess) {
numWorkers = len(toProcess)
}
type indexedResult struct {
idx int
result source.ParseResult
}
work := make(chan int, len(toProcess))
results := make([]source.ParseResult, len(toProcess))
var wg sync.WaitGroup
var processed atomic.Int64
// Feed work
for i := range toProcess {
work <- i
}
close(work)
// Spawn workers
wg.Add(numWorkers)
for w := 0; w < numWorkers; w++ {
go func() {
defer wg.Done()
for idx := range work {
results[idx] = source.ParseFile(toProcess[idx])
n := processed.Add(1)
if progressFn != nil {
progressFn(int(n), len(toProcess))
}
}
}()
}
wg.Wait()
// Collect results
for _, pr := range results {
if pr.Err != nil {
result.FileErrors++
continue
}
result.ParsedFiles++
result.ParseErrors += pr.ParseErrors
if pr.Stats.APICalls > 0 || pr.Stats.UserMessages > 0 {
result.Sessions = append(result.Sessions, pr.Stats)
}
}
return result, nil
}